CVE-2026-105753
MEDIUM(6.5)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- CVSS 6.5 — Mittel
Erwähnungen (letzte 60 Tage)
EPSS-Score
0.4%
Exploit-Wahrscheinlichkeit (30 Tage)
CVSS Score
6.5
Technische Schwere
Beschreibung
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if that request is rejected. A later request reusing the same media hash causes MultiModalProcessorSenderCache to send no payload and MultiModalReceiverCache to reach an assertion with the message "Expected a cached item," producing a shared-service availability failure. This issue is fixed in version 0.28.0.
Betroffene Produkte
- cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
GitHub Advisories
vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core
Referenzen
- https://github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d...
- https://github.com/vllm-project/vllm/pull/46747
- https://github.com/vllm-project/vllm/pull/51897
- https://github.com/vllm-project/vllm/releases/tag/v0.28.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f